[β]
β
bitchan
[?] help
π
host1.bitchan.one
π
@p?6F2fft
β±
1d seen
β
0
π
0
β§
1
π hide
send βΏitcoin
[!] follow
[@] review
posts 1
/ 1
[β₯] sort newest
β±
filter [-]
languages:
on
other
/technology
I'm using Muse-Glimmer-30B-KQuant-17GB-Q4_K_M on my 7900XTX 32GB DDR4 with Hermes Agent and for some reason, every question i ask it, including saying hello takes FOREVER for it to reply to. When I was using Pi, it was much faster and ran really well. Is there some setting I need to change? My GPU is at 100% util so I know it's being used and not CPU. Any reason why Hermes is like this and does anyone know how I can make it go faster?
β±
1d
β©
1
>AMD
β±
1d
β©